{"id":"W4401752756","doi":"10.1109/ichi61247.2024.00089","title":"Seeing Beyond Borders: Evaluating LLMs in Multilingual Ophthalmological Question Answering","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Question answering; Computer science; Natural language processing; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001091795,0.0001147473,0.00011685,0.0001477624,0.00005350223,0.0002444334,0.0003531978,0.00007613174,0.00003530511],"category_scores_gemma":[0.0001769202,0.0001009474,0.00003960626,0.0003378292,0.0000165107,0.0005126885,0.0002308423,0.0002386098,0.0000303468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000799533,"about_ca_system_score_gemma":0.00007727188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002183897,"about_ca_topic_score_gemma":0.00002126351,"domain_scores_codex":[0.9985847,0.00009204051,0.0002745309,0.0005126967,0.0002575295,0.0002785323],"domain_scores_gemma":[0.999473,0.0001722227,0.00002006622,0.0002558389,0.00003104744,0.00004776075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005189554,0.00005957639,0.004889646,0.0000996923,0.00001346656,0.0006983147,0.004517469,0.06078568,0.01044004,0.1061277,0.00001734922,0.8123459],"study_design_scores_gemma":[0.0001039547,0.00004686558,0.0008869324,0.0001057292,0.000001640852,0.00006789849,0.00009807943,0.9908959,0.0008804911,0.006731258,0.00005112937,0.000130173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5501434,0.0003876089,0.4450316,0.0003660423,0.0004347181,0.00009043214,1.209807e-7,0.0003195956,0.003226465],"genre_scores_gemma":[0.8018667,0.000002992331,0.1978185,0.00006804157,0.00007324263,0.000009015721,6.524052e-7,0.000006250339,0.0001546749],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9301102,"threshold_uncertainty_score":0.4116514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0550715705987934,"score_gpt":0.3926561732002667,"score_spread":0.3375846026014733,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}